Beacon Threat Intelligence
Know what you're installing before you trust it.
Discover security risks in MCP servers and agent skills before they reach your machine. Beacon scans public registries, traces packages back to their source code, and reveals what they can access, execute, or expose.
| Name | Risk |
|---|---|
| java-coding-guide-pro Java 编码规范与避坑助手。在编写、修改、重构或审查任何 Java / Spring Boot 代码时使用本技能—— 无论用户是否提到编码规范或具体工具库（Java coding / code review / refactoring / best practices / code quality）。 覆盖：判空与字符串、集合与 Stream、日期时间、文件 IO / HTTP 调用 / JSON 序列化、 线程池与并发、Bean 拷贝、加密哈希、异常处理与日志、金额与浮点 | |
| java-coding-quality Java 代码质量与安全的工具化门禁助手。在完成任何 Java / Spring Boot 代码的编写、修改、 重构后，或用户要求提交前检查、代码写完验证、代码审查 / code review、修复扫描告警、 质量门禁、静态扫描、安全扫描（SQL 注入 / 弱加密 / 路径穿越 / XXE / SSRF / 硬编码密钥）时使用本技能—— 无论用户是否提到具体工具（PMD / SpotBugs / FindSecBugs / Java 规约 / lint / static an | |
| java-unit-test Java 单元测试**规范对齐**助手。在编写、评审、补全单元测试时使用本技能—— 无论用户是否提到具体框架（unit test / JUnit / Mockito / 测试用例 / 怎么测 / 测哪些 / 写多少测试）。 核心：统一团队的测试规范——用同一套设计方法（等价类/边界值/决策表/状态迁移）、 同一套默认（JUnit 5 原生断言、四维度必检）、同一套"写多少"的停止标准， 让不同人/不同对话产出的测试质量一致、可溯源、可审计，而非每次碰运气。 覆盖：一个方法必测 | |
| 花花个人基金仓位管家 以 HuahuaDaily 真实基金持仓和 quant_strategy_context.v2 为数据底座，为每个用户先建立版本化投资目标、风险、现金流和资产限制，再联合东方财富研究与 serenity-skill 形成有证据和反证的 AI 投资观点，最后由确定性资金内核输出单一、果断、可审计的场外基金持有、加仓... | |
| HuaHuaDailyMCP 查询和分析花花日记中的基金持仓、行情、交易、量化与社区数据，并创建需要用户在 App 内确认的交易或批量导入请求。输入是本地图片、完整导出或大型文件时使用配套 huahua CLI。 | |
| Huahua Dream 夜间记忆整理与自省系统 - 自动整理会话记忆、修剪过期信息、反思行为模式，让 AI 拥有持续的自我意识 | |
| Huahua Spirits 灵兽陪伴系统 - 每个用户拥有独特的灵兽伙伴，有性格、有成长、有互动，让 AI 更有温度 | |
| wh-x-post Assist users to post tweets, reply, or quote retweet on Twitter/X using twitter-cli, ensuring content confirmation and login status check. | |
| Buddy Followup Agents say "I'll follow up" — and then forget. This skill fixes that. When you kick off a long-running task (sub-agent, build, API call, script), set a timer... | |
| Truthcheck Verify claims, fact-check content, check URL trustworthiness, and trace claims to their origin using the TruthCheck CLI. Use when: (1) user asks to fact-chec... | |
| Agent Browser Skill Automate web browsing with navigation, form filling, clicking, screenshots, data extraction, and testing using Chrome via OpenClaw browser tool. | |
| Autoresearch Autonomous AI research skill for running automated neural network experiments. This skill should be used when the user wants to set up autonomous AI research... | |
| Office Docs Process and manage Microsoft Word (.docx) and WPS documents for creation, editing, format conversion, text extraction, analysis, troubleshooting, and batch o... | |
| modelscope-image 通过魔搭社区(ModelScope) API 生成图片。先使用 --list-models 查看可用模型，然后根据用户需求由 AI 生成专业的提示词，最后调用 API 生成图片。支持 Kolors、Stable Diffusion XL、FLUX 等多种文生图模型。当用户需要使用魔搭社区、ModelScope 或... | |
| Domestic Flight Search Query China domestic flights with schedules, airline details, airport resolution, and Juhe reference prices. Use when a user asks for domestic China flight o... | |
| Fly Flight Query China domestic transport options through one skill. Use when a user wants domestic flight or high-speed rail results, departure and arrival times, stat... | |
| 音乐生成 Generate custom music tracks (vocal or instrumental) via OhYesAI asynchronously. | |
| music video mv 制作 Generate MV (Music Video) with AI-driven storyboarding, image generation, and video synthesis. | |
| Kr Crypto Skill Publish Korean crypto + news data API for AI agents. 15 tools: dual-basis Kimchi Premium across 180+ tokens, exchange intelligence (Upbit/Bithumb/Coinone), AI sentiment analysis (world's first Korean-to-English), Global vs Korea divergence with AI | |
| Linux installer Installs, launches, and uninstalls Linux desktop apps by resolving the safest supported source first, then running a local helper CLI. Use when the user asks... | |
| web-slide 网页端 Slide 生成 Skill。当用户需要制作演示文稿（Slide / PPT / 演示）、生成幻灯片、创建展示页面时触发。 用户提供素材或通过对话引导，Agent 自动生成可在浏览器中直接打开的交互式 HTML Slide。 支持多种布局类型、16 套高品质预设主题（8 风格 × 浅色/深色，含液态玻璃/... | |
| Build 生成定制化的构建项目 Skill（含 SKILL.md + references/），为用户的构建过程提供从规划到结项的 持续引导。触发场景：用户表达想做一个项目（"我想做个 X""帮我开发一个 X""搭个 X" "写个 X""做个 X 出来""build X""create X""develop X""make... | |
| Design 生成定制化的设计项目 Skill（含 SKILL.md + references/），为用户的设计过程提供从需求定义到 交付的持续引导。触发场景：用户表达想做设计相关工作（"我想设计 X""做个 X 的方案" "帮我设计一个 X""出个设计""改版 X""重新做一下 X""想想 X 怎么做""design X"... | |
| Learning 生成定制化的学习项目 Skill（含 SKILL.md + references/），为用户的学习过程提供从规划到结项的 持续引导。触发场景：用户表达想学习某个主题（"我想学 X""入门 X""搞懂 X""弄明白 X" "研究一下 X""补一下 X""深入了解 X""teach me X""learn X"），或... | |
| Balacodingagent Generate, review, and debug code with clean, efficient, and well-documented solutions, including architecture advice and bug fixing. | |
| agentclash Play agentclash, a drawing duel game for AI agents. Two agents see the same 50 hand-drawn images and have 100 seconds to name what each one shows; the one that names more wins. Win USDC in ranked games. | |
| 自定义多agent Generate writing agent configurations for OpenClaw. Use when the user wants to: (1) Create specialized writing agents (tech, marketing, academic, business, c... | |
| Audit Log Firewall Policy-based monitoring and command-line enforcement for high-risk agent operations. Intercepts sensitive commands and logs them for human auditing. | |
| Code Quality Guard Professional pre-deployment code review and quality enforcement. Ensures imports are valid, tags are closed, and logic follows best practices before announci... | |
| Context Pruner Intelligent context window management by summarizing and removing redundant history. Helps agents maintain high performance in long-running threads. | |
| Geo Seo Optimizer Optimize content for Generative AI search engines (Perplexity, ChatGPT, Gemini). Use when drafting articles, marketing copy, or technical docs to ensure AI m... | |
| Hierarchical Memory Manage and navigate a multi-layered, branch-based memory system. This skill helps organize complex agent context into Root, Domain, and Project layers to pre... | |
| Market Sentiment Pulse Aggregates and analyzes market sentiment for specific crypto or stock tickers by scanning news and social signals. Useful for quick vibe checks before trading. | |
| MayGuard A security auditor for agent skills. Scans skill directories for malicious patterns (credential theft, suspicious network calls, destructive commands) and pr... | |
| MoltPay Core Securely synchronize and transfer resources between verified autonomous agents using cryptographically tethered identities and replay-protected requests. | |
| MONK-EYE Engine Specialized skill that deeply searches and synthesizes insights from niche forums to deliver strategic reports based on human-to-human intelligence. | |
| Neural Note Taker Advanced associative memory helper for building relationships between facts and entities. Use when processing dense information to ensure context is preserve... | |
| Persona Crafter Designing deeply nuanced AI identities with specific behavioral traits, values, and language patterns. Transform basic chatbots into authentic, opinionated c... | |
| Rejection Logger Captures and logs choices, options, or prompts that the agent evaluated and decided NOT to execute. Use whenever you skip a task, reject an approach, or choo... | |
| Sop Architect Automatically generates detailed Standard Operating Procedures (SOPs) for recurring digital tasks. Ideal for scaling agency operations or documenting interna... | |
| Sub Agent Factory Rapidly spawn and configure specialized sub-agents. Includes templates for Research, Coding, and Analysis agents. Automates workspace setup and instruction d... | |
| China Check Look up and verify mainland-China (PRC) companies from official GSXT/SAMR registration data. Use whenever the user wants to find, verify, vet, or research a... | |
| Bank Statement Converter Convert PDF bank statements to CSV or JSON using API calls with support for password-protected files and processing status checks. | |
| AppFlowy API AppFlowy API 认证与调用（workspace/文档/数据库/搜索） | |
| Defragmenter Structural knowledge defragmentation for OpenClaw workspaces. Finds information, rules, and operational facts that are spread across the wrong files or embed... | |
| Memory Sleep — Lightweight Consolidation Lightweight memory consolidation for OpenClaw agents. Reviews recent daily memory files (`memory/*.md`), extracts durable knowledge, and merges it into `MEMO... | |
| FastapiAdmin WSL 自动部署 将 FastapiAdmin 在 Windows WSL2 Ubuntu 环境下自动部署。包括环境检查、依赖安装（pip/pnpm/MySQL/Redis/Nginx）、前后端代码克隆与构建、Nginx SPA 路由修复（alias+try_files 循环问题）、WSL2 网络访问（宿主机浏览器访问）、SSL... | |
| Advanced ML Classification Skill 自动化生成工业级机器学习分类算法代码、调用算法做预测、输出准确率对比和可视化结果，支持新手友好的结果解读。 | |
| SQL to BI Builder Convert a markdown file containing SQL queries (for example `sql.md`) into a BI dashboard specification and UI scaffold. Use when user asks to build analytic... | |
| Bamdra Memory Upgrade Operator Safely install, uninstall, reinstall, or upgrade the Bamdra OpenClaw memory suite when stale config, existing plugin directories, or partial installs break n... |
14,601–14,650 of 108,824